Text Chunker for RAG
Split text into embedding-ready chunks
Your text
Strategy
Token counts are exact (the GPT tokenizer runs in your browser, nothing is uploaded). Overlap repeats the trailing tokens of each chunk at the start of the next, so ideas that straddle a boundary still appear whole somewhere. Pairs with the token counter.
Related tools
More browser-only tools, free and no upload.
Redact PII & Secrets
Strip sensitive data before sending to an LLM
Text Summarizer
Cut long text to its key sentences
LLM Token Counter
Exact GPT tokens + cost per model
View Word (.docx)
Read .docx without Word
View Excel (.xlsx)
Read .xlsx without Excel
View PowerPoint (.pptx)
Read .pptx without PowerPoint
View JSON
Pretty-print + validate JSON
View CSV
Sortable table + JSON export
Questions
- Is Text Chunker for RAG free?
- Yes. Text Chunker for RAG is completely free, with no account, no sign-up, and no usage limits. It runs entirely in your browser.
- Do my files get uploaded when I use Text Chunker for RAG?
- No. Text Chunker for RAG processes everything on your device, so your files and text never leave your browser. You can verify it yourself: open your browser's Network tab and you'll see no uploads.
- How do I use Text Chunker for RAG?
- Open Text Chunker for RAG in your browser, no install or sign-up needed, then paste, type, or drop in your input and the result appears instantly. Split long documents into token-bounded chunks for embeddings and RAG pipelines, with configurable overlap and sentence-, paragraph-, or fixed-window strategies. Token counts are exact (GPT tokenizer) and everything runs in your browser, paste text, get clean chunks, copy them as JSON or download. Nothing uploaded, no API.
- Is there a file size limit in Text Chunker for RAG?
- There's no hard file or text size limit. Because Text Chunker for RAG runs locally in your browser, the only ceiling is your device's available memory, and everyday files process instantly.